Data verified: Nov 18, 2026, 3:00 AM UTC · Prices sourced from official provider pages. Verify current rates before production use.
Loading content…
Data verified: Nov 18, 2026, 3:00 AM UTC · Prices sourced from official provider pages. Verify current rates before production use.
Price, context and performance head to head. Data synced from the provider catalog.
Cheaper
Mistral Small 4
Larger context
Tied
Faster
Mistral Small 4
Higher quality
Mistral Medium 3.5
| Feature | Mistral Medium 3.5 | Mistral Small 4 |
|---|---|---|
| Provider | Mistral | Mistral |
| Tier | Mid-tier | Budget |
| Input per 1M tokens | $1.5 | $0.15 |
| Output per 1M tokens | $7.5 | $0.6 |
| Cached input per 1M | $1.5 | $0.015 |
| Context window | 262.1K | 262.1K |
| Intelligence index | 5/100 | 4/100 |
| Coding index | 47/100 | 27/100 |
| Agentic index | 7/100 | 0.80 |
| GPQA Diamond | — | 0.76 |
| Tau-bench (airline) | — | 0.46 |
| Speed | Standard | Fast |
| Vision (image input) | Yes | Yes |
| Function calling | Yes | Yes |
| Batch API | No | No |
Enter how many requests per day you send with an average prompt (1K input + 1K output) and compare the monthly cost of both models.
Mistral Small 4 saves $24.7/mo vs Mistral Medium 3.5
Want us to build it for you?
We integrate Mistral Medium 3.5 or Mistral Small 4 into your product with caching, observability and continuous evaluation — typically 40-80% cheaper than the obvious first pick.
Other combinations developers frequently compare in 2026.
What people ask us when comparing GPT, Claude, Gemini and the rest.